Method of quick fault diagnosis and new knowledge obtainment for high voltage circuit breaker expert system

High voltage circuit breaker is one of the key parts of power system, quick fault diagnosis of circuit breaker is of important to the quick discover of the fault cause, solve the fault source, and make sure the rapidly recovery of power system. In this paper, an improved algorithm of general radial basis function neural network (RBFNN) is introduced, based on improved algorithm, the neural network realizes quick fault diagnosis and self-refresh of neural network, and the neural network is applied to the on-line fault diagnosis expert system. The expert system deal with the fault data that sent from on-line monitoring equipment by using neural network, and can discover the fault type and give reasonable solution by forward reasoning. Meanwhile, the expert system has the ability of achieving new knowledge based on the application of self-refresh ability of RBF neural network.